Skip to main content

Episode 4 — Your first agent

An agent built end to end on camera in the earlier agent editor — name, instructions, knowledge scope, tools, model — with the trust boundary spelled out; the screens have changed since, the reasoning has not.

2 min read

Chat taught you to ask; knowledge taught you what answers stand on. This episode builds the thing that puts both to work: an agent, created from scratch on camera. The through-line is the trust boundary — every tool you grant widens what the agent can do, so the smallest agent that does the job is the safest one.

Episode 4 — Your first agent (2:46, captions available)

What the episode shows

AtScene
0:13The agents list — builtins, and where yours will live
0:26Create: a technical name, a display name, continue
0:43Instructions — the job description, including the hand-off rule
1:00Knowledge scope: the smallest library that does the job
1:13Tools: capability is exposure — start with none
1:33The model and its fallback
1:44Visible in chat, then the first live ask
2:06Iterate freely: versions keep every draft

Where to go next

Agent concepts is the mental model behind the four decisions, and Build your first agent walks them on the screens this version ships — a project agent with a harness, a model, and instructions, put to work on a task. Project agents is the field-by-field reference. The create dialog and the Tools, Knowledge, and History tabs the episode shows are not part of this version; the settings they carried live on the project agent's dialog now.

© 2026 Tale by Ruler GmbH — ISO 27001 & SOC 2 certified.

Tale is MIT licensed — free to use, modify, and distribute.